© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75168
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "one" and its variations, indicating a focus on individual or singular references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oretical
    -0.07
     aller
    -0.07
    ares
    -0.07
    ila
    -0.06
    ï¸
    -0.06
    Ïĩν
    -0.06
    allo
    -0.06
    alyze
    -0.06
    rud
    -0.06
    ories
    -0.06
    POSITIVE LOGITS
    gart
    0.07
    inous
    0.07
    gard
    0.07
    flen
    0.07
     opposed
    0.06
    ymb
    0.06
    ÂĬ
    0.06
     prepares
    0.06
    ovic
    0.06
    atoi
    0.06
    Activations Density 0.003%

    No Known Activations